Global forecasting of atmospheric CO₂ concentrations using a hybrid STL-Prophet-LSTM model

The increasing concentration of atmospheric carbon dioxide (CO₂) poses a significant global challenge, underscoring the need for accurate predictions to better understand and mitigate climate change. While existing CO₂ forecasting models are often restricted to specific scenarios or localized regions, a comprehensive global prediction framework remains lacking. To address this gap, we propose the SPL (STL-Prophet-LSTM) model, an integrated approach combining Seasonal-Trend decomposition using Loess (STL), the Prophet forecasting model, and Long Short-Term Memory (LSTM) networks. Leveraging monthly average CO₂ concentration data from six globally distributed monitoring stations (NOAA), we forecasted CO₂ trends over the next decade. Our results demonstrate the SPL model’s superior predictive performance, achieving an average RMSE of 0.67, MAE of 0.53, and R² of 0.99—outperforming benchmark models (ARIMA, SARIMA, Prophet, and standalone LSTM). Projections reveal a concerning upward trajectory, with Northern Hemisphere CO₂ levels expected to reach 450 ppm by 2032, compared to 438 ppm in the Southern Hemisphere, highlighting persistent hemispheric disparities. This study provides a robust methodological framework for global-scale CO₂ concentration forecasting, offering critical insights for climate policy and mitigation strategies.

大气二氧化碳（carbon dioxide, CO₂）浓度的持续攀升是一项严峻的全球性挑战，凸显了开展精准预测以更好地认知并减缓气候变化的迫切需求。现有二氧化碳预测模型往往局限于特定场景或局部区域，目前仍缺乏全面的全球预测框架。为填补这一研究空白，我们提出了SPL（STL-Prophet-LSTM）模型，这是一种融合基于Loess的季节性-趋势分解（Seasonal-Trend decomposition using Loess, STL）、Prophet预测模型与长短期记忆（Long Short-Term Memory, LSTM）网络的集成建模方法。我们借助来自全球6个分布式监测站点（美国国家海洋和大气管理局，NOAA）的月均二氧化碳浓度数据，对未来十年的二氧化碳浓度趋势进行了预测。研究结果证实了SPL模型的优异预测性能：其平均均方根误差（Root Mean Square Error, RMSE）为0.67、平均绝对误差（Mean Absolute Error, MAE）为0.53，决定系数（coefficient of determination, R²）达0.99，各项指标均优于基准模型（自回归积分滑动平均模型ARIMA、季节性自回归积分滑动平均模型SARIMA、Prophet以及单一LSTM模型）。预测结果显示出令人担忧的上升态势：预计到2032年，北半球二氧化碳浓度将达到450 ppm，而南半球仅为438 ppm，这凸显了南北半球之间持续存在的浓度差异。本研究为全球尺度的二氧化碳浓度预测提供了一套稳健的方法论框架，可为气候政策制定与减缓策略提供关键参考依据。

搜集汇总

背景与挑战

背景概述

该数据集提供了一个用于全球大气二氧化碳（CO2）浓度预测的混合STL-Prophet-LSTM（SPL）模型框架，旨在弥补现有模型在全局预测方面的不足。它基于美国国家海洋和大气管理局（NOAA）六个全球监测站的月平均CO2浓度数据，预测未来十年的趋势，并显示模型在RMSE、MAE和R2指标上优于传统基准模型。预测结果揭示了北半球和南半球CO2浓度将持续上升且存在差异，为气候政策和减缓策略提供了关键见解。